{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T09:08:44Z","timestamp":1779527324028,"version":"3.53.1"},"reference-count":116,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100010577","name":"Toyota Motor Europe","doi-asserted-by":"publisher","award":["TRACE-Z\u00fcrich"],"award-info":[{"award-number":["TRACE-Z\u00fcrich"]}],"id":[{"id":"10.13039\/501100010577","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476143"],"award-info":[{"award-number":["62476143"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["Nankai University, No. 070-63253235"],"award-info":[{"award-number":["Nankai University, No. 070-63253235"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["62576176"],"award-info":[{"award-number":["62576176"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["Nankai University, No. 070-63253270"],"award-info":[{"award-number":["Nankai University, No. 070-63253270"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1007\/s11263-026-02846-8","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T03:27:12Z","timestamp":1777260432000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RGB-D Indiscernible Object Counting in Underwater Scenes"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8667-9656","authenticated-orcid":false,"given":"Guolei","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaogang","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaochong","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6143-0264","authenticated-orcid":false,"given":"Yun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deng-Ping","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"issue":"4","key":"2846_CR1","first-page":"103","volume":"6","author":"MM Alam","year":"2019","unstructured":"Alam, M. M., & Islam, M. T. (2019). Machine learning approach of automatic identification and counting of blood cells. HTL, 6(4), 103\u2013108.","journal-title":"HTL"},{"key":"2846_CR2","doi-asserted-by":"publisher","first-page":"48810","DOI":"10.52202\/079017-1547","volume":"37","author":"N Amini-Naieni","year":"2024","unstructured":"Amini-Naieni, N., Han, T., & Zisserman, A. (2024). Countgd: Multi-modal open-world counting. Advances in Neural Information Processing Systems, 37, 48810\u201348837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2846_CR3","doi-asserted-by":"crossref","unstructured":"Arteta, C., Lempitsky, V., & Zisserman, A. (2016). Counting in the wild. In: ECCV.","DOI":"10.1007\/978-3-319-46478-7_30"},{"key":"2846_CR4","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., & Lee, Y.J. (2019). Yolact: Real-time instance segmentation. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2019.00925"},{"key":"2846_CR5","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In: ECCV.","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"1","key":"2846_CR6","first-page":"41","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R. (1997). Multitask learning. ML, 28(1), 41\u201375.","journal-title":"Multitask learning. ML"},{"key":"2846_CR7","doi-asserted-by":"crossref","unstructured":"Chan, A.B., & Vasconcelos, N. (2009). Bayesian poisson regression for crowd counting. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2009.5459191"},{"key":"2846_CR8","doi-asserted-by":"crossref","unstructured":"Chan, A.B., Liang, Z.-S.J., & Vasconcelos, N. (2008). Privacy preserving crowd monitoring: Counting people without people models or tracking. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"2846_CR9","doi-asserted-by":"crossref","unstructured":"Chattopadhyay, P., Vedantam, R., Selvaraju, R.R., Batra, D., & Parikh, D. (2017). Counting everyday objects in everyday scenes. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2017.471"},{"key":"2846_CR10","doi-asserted-by":"crossref","unstructured":"Chen, K., Loy, C.C., Gong, S., & Xiang, T. (2012). Feature mining for localised crowd counting. In: BMVC.","DOI":"10.5244\/C.26.21"},{"key":"2846_CR11","doi-asserted-by":"crossref","unstructured":"Chen, B., Yan, Z., Li, K., Li, P., Wang, B., Zuo, W., & Zhang, L. (2021). Variational attention: Propagating domain-specific knowledge for multi-domain learning in crowd counting. In: IEEE ICCV.","DOI":"10.1109\/ICCV48922.2021.01576"},{"key":"2846_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, Z.-Q., Dai, Q., Li, H., Song, J., Wu, X., & Hauptmann, A.G. (2022). Rethinking spatial invariance of convolutional networks for object counting. In: IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.01902"},{"key":"2846_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, X., Xiong, H., Fan, D.-P., Zhong, Y., Harandi, M., Drummond, T., & Ge, Z. (2022). Implicit motion handling for video camouflaged object detection. In: IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.01349"},{"issue":"4","key":"2846_CR14","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE TPAMI, 40(4), 834\u2013848.","journal-title":"IEEE TPAMI"},{"key":"2846_CR15","doi-asserted-by":"crossref","unstructured":"Cholakkal, H., Sun, G., Khan, F.S., & Shao, L. (2019). Object counting and instance segmentation with image-level supervision. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2019.01268"},{"issue":"3","key":"2846_CR16","doi-asserted-by":"publisher","first-page":"1604","DOI":"10.1109\/TPAMI.2020.3021025","volume":"44","author":"H Cholakkal","year":"2022","unstructured":"Cholakkal, H., Sun, G., Khan, S., Khan, F. S., Shao, L., & Van Gool, L. (2022). Towards partial supervision for generic object counting in natural scenes. IEEE TPAMI, 44(3), 1604\u20131622.","journal-title":"IEEE TPAMI"},{"key":"2846_CR17","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2846_CR18","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S., et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR."},{"issue":"1","key":"2846_CR19","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S., Van Gool, L., Williams, C. K., Winn, J., & Zisserman, A. (2015). The pascal visual object classes challenge: A retrospective. IJCV, 111(1), 98\u2013136.","journal-title":"IJCV"},{"key":"2846_CR20","doi-asserted-by":"crossref","unstructured":"Fan, D.-P., Ji, G.-P., Sun, G., Cheng, M.-M., Shen, J., & Shao, L. (2020). Camouflaged object detection. In: IEEE CVPR.","DOI":"10.1109\/CVPR42600.2020.00285"},{"issue":"10","key":"2846_CR21","first-page":"6024","volume":"44","author":"D-P Fan","year":"2022","unstructured":"Fan, D.-P., Ji, G.-P., Cheng, M.-M., & Shao, L. (2022). Concealed object detection. IEEE TPAMI, 44(10), 6024\u20136042.","journal-title":"Concealed object detection. IEEE TPAMI"},{"key":"2846_CR22","doi-asserted-by":"crossref","unstructured":"Ge, W., & Collins, R.T. (2009). Marked point processes for crowd counting. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2009.5206621"},{"key":"2846_CR23","doi-asserted-by":"crossref","unstructured":"Gong, S., Zhang, S., Yang, J., Dai, D., & Schiele, B. (2022). Bi-level alignment for cross-domain crowd counting. In: IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.00739"},{"key":"2846_CR24","doi-asserted-by":"crossref","unstructured":"Han, D., Ye, T., Han, Y., Xia, Z., Pan, S., Wan, P., Song, S., & Huang, G. (2024). Agent attention: On the integration of softmax and linear attention. In: ECCV","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"2846_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2017.322"},{"key":"2846_CR26","doi-asserted-by":"crossref","unstructured":"He, Y., Ma, Z., Wei, X., Hong, X., Ke, W., & Gong, Y. (2021). Error-aware density isomorphism reconstruction for unsupervised cross-domain crowd counting. In: AAAI.","DOI":"10.1609\/aaai.v35i2.16245"},{"key":"2846_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J. (2016). Deep residual learning for image recognition. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2846_CR28","doi-asserted-by":"crossref","unstructured":"Hsieh, M.-R., Lin, Y.-L., & Hsu, W.H. (2017). Drone-based object counting by spatially regularized regional proposal network. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2017.446"},{"key":"2846_CR29","doi-asserted-by":"crossref","unstructured":"Idrees, H., Saleemi, I., Seibert, C., & Shah, M. (2013). Multi-source multi-scale counting in extremely dense crowd images. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2013.329"},{"key":"2846_CR30","doi-asserted-by":"crossref","unstructured":"Idrees, H., Tayyab, M., Athrey, K., Zhang, D., Al-Maadeed, S., Rajpoot, N., & Shah, M. (2018). Composition loss for counting, density map estimation and localization in dense crowds. In: ECCV.","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"2846_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, X., Zhang, L., Xu, M., Zhang, T., Lv, P., Zhou, B., Yang, X., & Pang, Y. (2020). Attention scaling for crowd counting. In: IEEE CVPR.","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"2846_CR32","unstructured":"Kingma, D.P., & Ba, J. (2015). Adam: A method for stochastic optimization. In: ICLR"},{"key":"2846_CR33","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, & W.-Y., et al. (2023). Segment anything. In: IEEE ICCV, pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2846_CR34","doi-asserted-by":"crossref","unstructured":"Lamdouar, H., Yang, C., Xie, W., & Zisserman, A. (2020). Betrayed by motion: Camouflaged object discovery via motion segmentation. In: ACCV.","DOI":"10.1007\/978-3-030-69532-3_30"},{"key":"2846_CR35","doi-asserted-by":"crossref","unstructured":"Laradji, I.H., Rostamzadeh, N., Pinheiro, P.O., Vazquez, D., & Schmidt, M. (2018). Where are the blobs: Counting by localization with point supervision. In: ECCV.","DOI":"10.1007\/978-3-030-01216-8_34"},{"key":"2846_CR36","first-page":"287","volume":"31","author":"T-N Le","year":"2021","unstructured":"Le, T.-N., Cao, Y., Nguyen, T.-C., Le, M.-Q., Nguyen, K.-D., Do, T.-T., Tran, M.-T., & Nguyen, T. V. (2021). Camouflaged instance segmentation in-the-wild: Dataset, method, and benchmark suite. IEEE TIP, 31, 287\u2013300.","journal-title":"IEEE TIP"},{"key":"2846_CR37","first-page":"45","volume":"184","author":"T-N Le","year":"2019","unstructured":"Le, T.-N., Nguyen, T. V., Nie, Z., Tran, M.-T., & Sugimoto, A. (2019). Anabranch network for camouflaged object segmentation. CVIU, 184, 45\u201356.","journal-title":"CVIU"},{"key":"2846_CR38","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, X., & Chen, D. (2018). CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2018.00120"},{"key":"2846_CR39","doi-asserted-by":"crossref","unstructured":"Li, M., Zhang, Z., Huang, K., & Tan, T. (2008). Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection. In: IEEE ICPR.","DOI":"10.1109\/ICPR.2008.4761705"},{"key":"2846_CR40","doi-asserted-by":"crossref","unstructured":"Lian, D., Li, J., Zheng, J., Luo, W., & Gao, S. (2019). Density map regression guided detection network for rgb-d crowd counting and localization. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2019.00192"},{"issue":"12","key":"2846_CR41","doi-asserted-by":"publisher","first-page":"9056","DOI":"10.1109\/TPAMI.2021.3124956","volume":"44","author":"D Lian","year":"2022","unstructured":"Lian, D., Chen, X., Li, J., Luo, W., & Gao, S. (2022). Locating and counting heads in crowds with a depth prior. IEEE TPAMI, 44(12), 9056\u20139072.","journal-title":"IEEE TPAMI"},{"key":"2846_CR42","doi-asserted-by":"crossref","unstructured":"Liang, D., Xu, W., & Bai, X. (2022). An end-to-end transformer model for crowd localization. In: ECCV.","DOI":"10.1007\/978-3-031-19769-7_3"},{"issue":"6","key":"2846_CR43","first-page":"1","volume":"65","author":"D Liang","year":"2022","unstructured":"Liang, D., Chen, X., Xu, W., Zhou, Y., & Bai, X. (2022). Transcrowd: weakly-supervised crowd counting with transformers. SCIS, 65(6), 1\u201314.","journal-title":"SCIS"},{"key":"2846_CR44","doi-asserted-by":"crossref","unstructured":"Lin, H., Ma, Z., Ji, R., Wang, Y., & Hong, X. (2022). Boosting crowd counting via multifaceted attention. In: IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.01901"},{"key":"2846_CR45","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C.L. (2014). Microsoft coco: Common objects in context. In: ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2846_CR46","doi-asserted-by":"crossref","unstructured":"Liu, C., Chen, L.-C., Schroff, F., Adam, H., Hua, W., Yuille, A.L., & Fei-Fei, L. (2019). Auto-deeplab: Hierarchical neural architecture search for semantic image segmentation. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2019.00017"},{"key":"2846_CR47","doi-asserted-by":"crossref","unstructured":"Liu, L., Chen, J., Wu, H., Li, G., Li, C., & Lin, L. (2021). Cross-modal collaborative representation learning and a large-scale rgbt benchmark for crowd counting. In: IEEE CVPR.","DOI":"10.1109\/CVPR46437.2021.00479"},{"key":"2846_CR48","doi-asserted-by":"crossref","unstructured":"Liu, W., Durasov, N., & Fua, P. (2022). Leveraging self-supervision for cross-domain crowd counting. In: IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.00527"},{"key":"2846_CR49","doi-asserted-by":"crossref","unstructured":"Liu, J., Gao, C., Meng, D., & Hauptmann, A.G. (2018). Decidenet: Counting varying density crowds through attention guided detection and density estimation. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2018.00545"},{"key":"2846_CR50","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2846_CR51","doi-asserted-by":"crossref","unstructured":"Liu, L., Lu, H., Zou, H., Xiong, H., Cao, Z., & Shen, C. (2020). Weighing counts: Sequential crowd counting by reinforcement learning. In: ECCV.","DOI":"10.1007\/978-3-030-58607-2_10"},{"key":"2846_CR52","doi-asserted-by":"crossref","unstructured":"Liu, L., Qiu, Z., Li, G., Liu, S., Ouyang, W., & Lin, L. (2019). Crowd counting with deep structured scale integration network. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2019.00186"},{"key":"2846_CR53","doi-asserted-by":"crossref","unstructured":"Liu, W., Salzmann, M., & Fua, P. (2019). Context-aware crowd counting. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2019.00524"},{"key":"2846_CR54","unstructured":"Liu, Z., Wu, W., Tan, Y., & Zhang, G. (2022). Rgb-t multi-modal crowd counting based on transformer. In: BMVC."},{"key":"2846_CR55","doi-asserted-by":"crossref","unstructured":"Liu, X., Yang, J., Ding, W., Wang, T., Wang, Z., & Xiong, J. (2020). Adaptive mixture regression network with local counting map for crowd counting. In: ECCV.","DOI":"10.1007\/978-3-030-58586-0_15"},{"key":"2846_CR56","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TMM.2023.3262978","volume":"26","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Cao, G., Shi, B., & Hu, Y. (2024). Ccanet: A collaborative cross-modal attention network for rgb-d crowd counting. IEEE Transactions on Multimedia, 26, 154\u2013165. https:\/\/doi.org\/10.1109\/TMM.2023.3262978","journal-title":"IEEE Transactions on Multimedia"},{"issue":"8","key":"2846_CR57","doi-asserted-by":"publisher","first-page":"1862","DOI":"10.1109\/TPAMI.2019.2899857","volume":"41","author":"X Liu","year":"2019","unstructured":"Liu, X., Van De Weijer, J., & Bagdanov, A. D. (2019). Exploiting unlabeled data in CNNs by self-supervised learning to rank. IEEE TPAMI, 41(8), 1862\u20131878.","journal-title":"IEEE TPAMI"},{"issue":"1","key":"2846_CR58","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1109\/TII.2022.3171352","volume":"19","author":"H Li","year":"2022","unstructured":"Li, H., Zhang, S., & Kong, W. (2022). Rgb-d crowd counting with cross-modal cycle-attention fusion and fine-coarse supervision. IEEE Transactions on Industrial Informatics, 19(1), 306\u2013316.","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"2846_CR59","doi-asserted-by":"crossref","unstructured":"Lu, H., Cao, Z., Xiao, Y., Zhuang, B., & Shen, C. (2017). Tasselnet: counting maize tassels in the wild via local counts regression network. PM 13(1), 79.","DOI":"10.1186\/s13007-017-0224-0"},{"key":"2846_CR60","unstructured":"Lyu, Y., Zhang, J., Dai, Y., Li, A., Liu, B., Barnes, N., & Fan, D.-P. (2021). Simultaneously localize, segment and rank the camouflaged objects. In: IEEE CVPR."},{"key":"2846_CR61","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, X., Hong, X., & Gong, Y. (2019). Bayesian loss for crowd count estimation with point supervision. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2019.00624"},{"key":"2846_CR62","doi-asserted-by":"crossref","unstructured":"Meng, H., Hong, X., Wang, C., Shang, M., & Zuo, W. (2024). Multi-modal crowd counting via a broker modality. In: ECCV.","DOI":"10.1007\/978-3-031-72904-1_14"},{"key":"2846_CR63","doi-asserted-by":"crossref","unstructured":"Meng, C., Liu, E., Neiswanger, W., Song, J., Burke, M., Lobell, D., & Ermon, S. (2021). Is-count: Large-scale object counting from satellite images with covariate-based importance sampling. arXiv preprint arXiv:2112.09126.","DOI":"10.1609\/aaai.v36i11.21462"},{"key":"2846_CR64","doi-asserted-by":"crossref","unstructured":"Mondal, A., Nag, S., Zhu, X., & Dutta, A. (2025). Omnicount: Multi-label object counting with semantic-geometric priors. In: AAAI, vol. 39, pp. 19537\u201319545.","DOI":"10.1609\/aaai.v39i18.34151"},{"key":"2846_CR65","doi-asserted-by":"crossref","unstructured":"Mu, B., Shao, F., Xie, Z., Chen, H., Jiang, Q., & Ho, Y.-S. (2024). Visual prompt multi-branch fusion network for rgb-thermal crowd counting. IEEE Internet of Things Journal.","DOI":"10.1109\/JIOT.2024.3420449"},{"key":"2846_CR66","doi-asserted-by":"crossref","unstructured":"Narayan, S., Cholakkal, H., Khan, F.S., & Shao, L. (2019). 3c-net: Category count and center loss for weakly-supervised action localization. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2019.00877"},{"key":"2846_CR67","doi-asserted-by":"crossref","unstructured":"Nguyen, H.-T., Ngo, C.-W., & Chan, W.-K. (2022). Sibnet: Food instance counting and segmentation. PR 124, 108470","DOI":"10.1016\/j.patcog.2021.108470"},{"issue":"25","key":"2846_CR68","doi-asserted-by":"publisher","first-page":"5716","DOI":"10.1073\/pnas.1719367115","volume":"115","author":"MS Norouzzadeh","year":"2018","unstructured":"Norouzzadeh, M. S., Nguyen, A., Kosmala, M., Swanson, A., Palmer, M. S., Packer, C., & Clune, J. (2018). Automatically identifying, counting, and describing wild animals in camera-trap images with deep learning. PNAS, 115(25), 5716\u20135725.","journal-title":"PNAS"},{"key":"2846_CR69","doi-asserted-by":"crossref","unstructured":"Onoro-Rubio, D., & L\u00f3pez-Sastre, R.J. (2016). Towards perspective-free object counting with deep learning. In: ECCV.","DOI":"10.1007\/978-3-319-46478-7_38"},{"key":"2846_CR70","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., & Antiga, L., et al. (2019). Pytorch: An imperative style, high-performance deep learning library. In: NeurIPS."},{"key":"2846_CR71","first-page":"66260","volume":"37","author":"J Pelhan","year":"2024","unstructured":"Pelhan, J., Lukezic, A., Zavrtanik, V., & Kristan, M. (2024). A novel unified architecture for low-shot counting by detection and segmentation. Advances in Neural Information Processing Systems, 37, 66260\u201366282.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2846_CR72","doi-asserted-by":"crossref","unstructured":"Peng, T., Li, Q., & Zhu, P. (2020). Rgb-t crowd counting from drone: A benchmark and mmccn network. In: ACCV.","DOI":"10.1007\/978-3-030-69544-6_30"},{"key":"2846_CR73","unstructured":"Qian, Y., Zhang, L., Hong, X., Donovan, C.R., & Arandjelovic, O. (2022). Segmentation assisted u-shaped multi-scale transformer for crowd counting. In: BMVC."},{"key":"2846_CR74","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Le, H., & Hoai, M. (2018). Iterative crowd counting. In: ECCV.","DOI":"10.1007\/978-3-030-01234-2_17"},{"issue":"8","key":"2846_CR75","first-page":"2739","volume":"43","author":"DB Sam","year":"2020","unstructured":"Sam, D. B., Peri, S. V., Sundararaman, M. N., Kamath, A., & Babu, R. V. (2020). Locate, size, and count: accurately resolving people in dense crowds via detection. IEEE TPAMI, 43(8), 2739\u20132751.","journal-title":"IEEE TPAMI"},{"key":"2846_CR76","doi-asserted-by":"crossref","unstructured":"Shi, Z., Mettes, P., Snoek, C.G.: Counting with focus for free. In: IEEE ICCV (2019)","DOI":"10.1109\/ICCV.2019.00430"},{"key":"2846_CR77","doi-asserted-by":"crossref","unstructured":"Shu, W., Wan, J., Tan, K.C., Kwong, S., & Chan, A.B. (2022). Crowd counting in the frequency domain. In: IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.01900"},{"key":"2846_CR78","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Yasarla, R., & Patel, V.M. (2019). Pushing the frontiers of unconstrained crowd counting: New dataset and benchmark method. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2019.00131"},{"issue":"5","key":"2846_CR79","first-page":"2594","volume":"44","author":"V Sindagi","year":"2022","unstructured":"Sindagi, V., Yasarla, R., & Patel, V. M. (2022). Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method. IEEE TPAMI, 44(5), 2594\u20132609.","journal-title":"IEEE TPAMI"},{"key":"2846_CR80","doi-asserted-by":"crossref","unstructured":"Song, Q., Wang, C., Jiang, Z., Wang, Y., Tai, Y., Wang, C., Li, J., Huang, F., & Wu, Y. (2021). Rethinking counting and localization in crowds: A purely point-based framework. In: IEEE ICCV.","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"2846_CR81","doi-asserted-by":"crossref","unstructured":"Song, Q., Wang, C., Wang, Y., Tai, Y., Wang, C., Li, J., Wu, J., & Ma, J. (2021). To choose or to fuse? scale selection for crowd counting. In: AAAI.","DOI":"10.1609\/aaai.v35i3.16360"},{"issue":"2","key":"2846_CR82","first-page":"1035","volume":"28","author":"T Stahl","year":"2018","unstructured":"Stahl, T., Pintea, S. L., & Van Gemert, J. C. (2018). Divide and count: Generic object counting by image divisions. IEEE TIP, 28(2), 1035\u20131044.","journal-title":"IEEE TIP"},{"key":"2846_CR83","doi-asserted-by":"crossref","unstructured":"Sun, G., An, Z., Liu, Y., Liu, C., Sakaridis, C., Fan, D.-P., & Van\u00a0Gool, L. (2023). Indiscernible object counting in underwater scenes. In: IEEE CVPR, 13791\u201313801.","DOI":"10.1109\/CVPR52729.2023.01325"},{"key":"2846_CR84","unstructured":"Sun, G., Liu, Y., Probst, T., Paudel, D.P., Popovic, N., & Van\u00a0Gool, L. (2021). Boosting crowd counting with transformers. arXiv preprint arXiv:2105.10926."},{"key":"2846_CR85","doi-asserted-by":"crossref","unstructured":"Sun, G., Probst, T., Paudel, D.P., Popovi\u0107, N., Kanakis, M., Patel, J., Dai, D., & Van\u00a0Gool, L. (2021). Task switching network for multi-task learning. In: IEEE ICCV.","DOI":"10.1109\/ICCV48922.2021.00818"},{"key":"2846_CR86","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In: NeurIPS."},{"key":"2846_CR87","doi-asserted-by":"crossref","unstructured":"Wan, J., & Chan, A. (2019). Adaptive density map generation for crowd counting. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2019.00122"},{"key":"2846_CR88","unstructured":"Wan, J., & Chan, A. (2020). Modeling noisy annotations for crowd counting. In: NeurIPS."},{"key":"2846_CR89","doi-asserted-by":"crossref","unstructured":"Wan, J., Liu, Z., & Chan, A.B. (2021). A generalized loss function for crowd counting and localization. In: IEEE CVPR.","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"2846_CR90","doi-asserted-by":"crossref","unstructured":"Wang, M., & Wang, X. (2011). Automatic adaptation of a generic pedestrian detector to a specific traffic scene. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2011.5995698"},{"key":"2846_CR91","doi-asserted-by":"crossref","unstructured":"Wang, Q., Gao, J., Lin, W., & Yuan, Y. (2019). Learning from synthetic data for crowd counting in the wild. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2019.00839"},{"key":"2846_CR92","unstructured":"Wang, C., Hong, X., Ma, Z., Wei, Y., Wang, Y., & Fan, X. (2024). Multi-modal crowd counting via modal emulation. In: BMVC."},{"key":"2846_CR93","unstructured":"Wang, B., Liu, H., Samaras, D., & Hoai, M. (2020). Distribution matching for crowd counting. In: NeurIPS."},{"key":"2846_CR94","doi-asserted-by":"crossref","unstructured":"Wang, C., Song, Q., Zhang, B., Wang, Y., Tai, Y., Hu, X., Wang, C., Li, J., Ma, J., & Wu, Y. (2021). Uniformity in heterogeneity: Diving deep into count interval partition for crowd counting. In: IEEE ICCV.","DOI":"10.1109\/ICCV48922.2021.00322"},{"key":"2846_CR95","doi-asserted-by":"crossref","unstructured":"Wang, L., Yang, J., Zhang, Y., Wang, F., & Zheng, F. (2024). Depth-aware concealed crop detection in dense agricultural scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17201\u201317211.","DOI":"10.1109\/CVPR52733.2024.01628"},{"key":"2846_CR96","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013269","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Gao, J., Lin, W., & Li, X. (2020). Nwpu-crowd: A large-scale benchmark for crowd counting and localization. IEEE TPAMI. https:\/\/doi.org\/10.1109\/TPAMI.2020.3013269","journal-title":"IEEE TPAMI"},{"issue":"3","key":"2846_CR97","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2022). Pvt v2: Improved baselines with pyramid vision transformer. Computational Visual Media, 8(3), 415\u2013424.","journal-title":"Computational Visual Media"},{"issue":"3","key":"2846_CR98","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1109\/TPAMI.2020.3022878","volume":"44","author":"J Wan","year":"2022","unstructured":"Wan, J., Wang, Q., & Chan, A. B. (2022). Kernel-based density map generation for dense object counting. IEEE TPAMI, 44(3), 1357\u20131370.","journal-title":"IEEE TPAMI"},{"key":"2846_CR99","doi-asserted-by":"crossref","unstructured":"Weinberger, K., Dasgupta, A., Langford, J., Smola, A., & Attenberg, J. (2009). Feature hashing for large scale multitask learning. In: ICML","DOI":"10.1145\/1553374.1553516"},{"key":"2846_CR100","doi-asserted-by":"crossref","unstructured":"Wen, L., Du, D., Zhu, P., Hu, Q., Wang, Q., Bo, L., & Lyu, S. (2021). Detection, tracking, and counting meets drones in crowds: A benchmark. In: IEEE CVPR.","DOI":"10.1109\/CVPR46437.2021.00772"},{"key":"2846_CR101","doi-asserted-by":"crossref","unstructured":"Wu, Z., Liu, L., Zhang, Y., Mao, M., Lin, L., & Li, G. (2022). Multimodal crowd counting with mutual attention transformers. In: IEEE ICME, pp. 1\u20136. IEEE.","DOI":"10.1109\/ICME52920.2022.9859777"},{"key":"2846_CR102","doi-asserted-by":"crossref","unstructured":"Xie, J., Cholakkal, H., Muhammad\u00a0Anwer, R., Shahbaz\u00a0Khan, F., Pang, Y., Shao, L., & Shah, M. (2020). Count-and similarity-aware r-cnn for pedestrian detection. In: ECCV.","DOI":"10.1007\/978-3-030-58520-4_6"},{"key":"2846_CR103","doi-asserted-by":"crossref","unstructured":"Xiong, H., & Yao, A. (2022). Discrete-constrained regression for local counting models. In: ECCV.","DOI":"10.1007\/978-3-031-20053-3_36"},{"key":"2846_CR104","doi-asserted-by":"crossref","unstructured":"Xiong, H., Lu, H., Liu, C., Liu, L., Cao, Z., & Shen, C. (2019). From open set to closed set: Counting objects by spatial divide-and-conquer. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2019.00845"},{"issue":"2","key":"2846_CR105","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/s11263-021-01542-z","volume":"130","author":"C Xu","year":"2022","unstructured":"Xu, C., Liang, D., Xu, Y., Bai, S., Zhan, W., Bai, X., & Tomizuka, M. (2022). Autoscale: Learning to scale for crowd counting. IJCV, 130(2), 405\u2013434.","journal-title":"IJCV"},{"key":"2846_CR106","doi-asserted-by":"crossref","unstructured":"Yan, Z., Yuan, Y., Zuo, W., Tan, X., Wang, Y., Wen, S., & Ding, E. (2019). Perspective-guided convolution networks for crowd counting. In: IEEE ICCV.","DOI":"10.1109\/ICCV.2019.00104"},{"key":"2846_CR107","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., & Zhao, H. (2024). Depth anything: Unleashing the power of large-scale unlabeled data. In: IEEE CVPR, pp. 10371\u201310381.","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"2846_CR108","unstructured":"Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., & Zhao, H. (2024). Depth anything v2. arXiv preprint arXiv:2406.09414."},{"key":"2846_CR109","doi-asserted-by":"crossref","unstructured":"Yang, Y., Li, G., Wu, Z., Su, L., Huang, Q., & Sebe, N. (2020). Weakly-supervised crowd counting learns from sorting rather than locations. In: ECCV.","DOI":"10.1007\/978-3-030-58598-3_1"},{"key":"2846_CR110","doi-asserted-by":"crossref","unstructured":"Yu, Z., Zhang, X., Zhao, L., Bin, Y., & Xiao, G. (2024). Exploring deeper! segment anything model with depth perception for camouflaged object detection. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 4322\u20134330.","DOI":"10.1145\/3664647.3681119"},{"key":"2846_CR111","doi-asserted-by":"crossref","unstructured":"Zand, M., Damirchi, H., Farley, A., Molahasani, M., Greenspan, M., & Etemad, A. (2022). Multiscale crowd counting and localization by multitask point supervision. In: IEEE ICASSP.","DOI":"10.1109\/ICASSP43922.2022.9747776"},{"key":"2846_CR112","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Choi, S., & Hong, S. (2022). Spatio-channel attention blocks for cross-modal crowd counting. In: ACCV, pp. 90\u2013107.","DOI":"10.1007\/978-3-031-26284-5_2"},{"key":"2846_CR113","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., & Ma, Y. (2016). Single-image crowd counting via multi-column convolutional neural network. In: IEEE CVPR.","DOI":"10.1109\/CVPR.2016.70"},{"issue":"6","key":"2846_CR114","first-page":"1048","volume":"18","author":"C Zhang","year":"2016","unstructured":"Zhang, C., Kang, K., Li, H., Wang, X., Xie, R., & Yang, X. (2016). Data-driven crowd understanding: A baseline for a large-scale crowd dataset. IEEE TMM, 18(6), 1048\u20131061.","journal-title":"IEEE TMM"},{"key":"2846_CR115","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Li, B., Tang, L., Kuang, S., Wu, S., & Ding, S. (2022). Detecting camouflaged object in frequency domain. In: IEEE CVPR.","DOI":"10.1109\/CVPR52688.2022.00446"},{"issue":"7","key":"2846_CR116","first-page":"3602","volume":"44","author":"JT Zhou","year":"2022","unstructured":"Zhou, J. T., Zhang, L., Du, J., Peng, X., Fang, Z., Xiao, Z., & Zhu, H. (2022). Locality-aware crowd counting. IEEE TPAMI, 44(7), 3602\u20133613.","journal-title":"Locality-aware crowd counting. IEEE TPAMI"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02846-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02846-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02846-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T08:44:13Z","timestamp":1779525853000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02846-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":116,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["2846"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02846-8","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"18 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"247"}}